.gitignore updated

.gitignore

@@ -0,0 +1,161 @@
+# User-defined
+*.txt
+*.csv
+*.yaml
+config.py
+passwords.txt
+training_images/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+

bulkpp

@@ -1 +1 @@
-Subproject commit 32d3febba22b73b37ac188d84330ae789288c535
+Subproject commit a25d1b578e93fa63bdc65c02a6c007cbec5b2aa0

pms.py

@@ -2,7 +2,7 @@ import seaborn as sns
 import numpy as np
 import matplotlib.pyplot as plt
 import re
-import bs4
+# import bs4
 from bs4 import BeautifulSoup as b
 import requests
 import time
@@ -14,17 +14,20 @@ while True:
     start = time.time()
 
     SQ = str(input())
-    SQ_1 = SQ.replace(' ', '+').replace('NEW','').replace('men', '').replace('women', '')
+    SQ_1 = SQ.replace(' ', '+').replace('NEW',
+                                        '').replace('men', '').replace('women', '')
     gender = ['Men', 'Women']
 
-    #&color[]=color
+    # &color[]=color
-    posh_colors = ['Red', 'Pink', 'Orange', 'Yellow', 'Green', 'Blue', 'Purple', 'Gold', 'Silver', 'Black', 'Gray', 'White', 'Cream', 'Brown', 'Tan']
+    posh_colors = ['Red', 'Pink', 'Orange', 'Yellow', 'Green', 'Blue', 'Purple',
+                   'Gold', 'Silver', 'Black', 'Gray', 'White', 'Cream', 'Brown', 'Tan']
 
-    for i in range(0,len(posh_colors)):
+    for i in range(0, len(posh_colors)):
         if posh_colors[i] in SQ:
             url_color = '&color[]=' + posh_colors[i]
             url_separator = "&availability=sold_out" + url_color + "&department=All&max_id="
-            url_separator1 = "&availability=sold_out" + url_color + "&condition=nwt_and_ret&department=All&max_id="
+            url_separator1 = "&availability=sold_out" + url_color + \
+                "&condition=nwt_and_ret&department=All&max_id="
             SQ_1 = SQ_1.replace(posh_colors[i], '')
             break
         else:
@@ -43,73 +46,72 @@ while True:
 
     html = requests.get(url).text
     html1 = requests.get(url_1).text
-    soup = b(html, "html.parser")
+    soup = b(html, "lxml")
-    soup1 = b(html1,'html.parser')
+    soup1 = b(html1, 'lxml')
 
     # Begin new and used condition items price list:
 
     for listing in soup.findAll("div", {"class": "item__details"}):
         price = listing.findAll("span", {"class": "p--t--1 fw--bold"})[0].text
         indices = price.find('$')
-            price = price[indices+1:]
+        price = price[indices + 1:]
         space = price.find(' ')
-            price = int(price[:space-1])
+        price = int(price[:space - 1])
         prices.append(price)
 
     while True:
-        last_page = soup.find_all(string = re.compile('No Listings Found'))
+        last_page = soup.find_all(string=re.compile('No Listings Found'))
         if last_page:
             break
         pg = pg + 1
         url = base_url + SQ_1 + url_separator + str(pg)
         html = requests.get(url).text
-        soup = b(html, "html.parser")
+        soup = b(html, "lxml")
-
 
         for listing in soup.findAll("div", {"class": "item__details"}):
-                price = listing.findAll("span", {"class": "p--t--1 fw--bold"})[0].text
+            price = listing.findAll(
-                #indices = [i for i, dollars in enumerate(price) if dollars == '$']
+                "span", {"class": "p--t--1 fw--bold"})[0].text
-                #price = int(price[1:indices[1]-1])
+            # indices = [i for i, dollars in enumerate(price) if dollars == '$']
+            # price = int(price[1:indices[1]-1])
             indices = price.find('$')
-                price = price[indices+1:]
+            price = price[indices + 1:]
             space = price.find(' ')
-                price = int(price[:space-1])
+            price = int(price[:space - 1])
             prices.append(price)
 
     # Begin new condition item prices list:
 
     for listing in soup1.findAll("div", {"class": "item__details"}):
         price1 = listing.findAll("span", {"class": "p--t--1 fw--bold"})[0].text
-            #indices = [i for i, dollars in enumerate(price1) if dollars == '$']
+        # indices = [i for i, dollars in enumerate(price1) if dollars == '$']
-            #price1 = int(price1[1:indices[1]-1])
+        # price1 = int(price1[1:indices[1]-1])
         indices = price1.find('$')
-            price1 = price1[indices+1:]
+        price1 = price1[indices + 1:]
         space = price1.find(' ')
-            price1 = int(price1[:space-1])
+        price1 = int(price1[:space - 1])
         prices1.append(price1)
 
     while True:
 
-        last_page = soup1.find_all(string = re.compile('No Listings Found'))
+        last_page = soup1.find_all(string=re.compile('No Listings Found'))
         if last_page:
             break
         pg = pg + 1
         url_1 = base_url + SQ_1 + url_separator1 + str(pg)
         html1 = requests.get(url_1).text
-        soup1 = b(html1, "html.parser")
+        soup1 = b(html1, "lxml")
-
 
         for listing in soup1.findAll("div", {"class": "item__details"}):
-                price1 = listing.findAll("span", {"class": "p--t--1 fw--bold"})[0].text
+            price1 = listing.findAll(
-                #indices = [i for i, dollars in enumerate(price1) if dollars == '$']
+                "span", {"class": "p--t--1 fw--bold"})[0].text
-                #price1 = int(price1[1:indices[1]-1])
+            # indices = [i for i, dollars in enumerate(price1) if dollars == '$']
+            # price1 = int(price1[1:indices[1]-1])
             indices = price1.find('$')
-                price1 = price1[indices+1:]
+            price1 = price1[indices + 1:]
             space = price1.find(' ')
-                price1 = int(price1[:space-1])
+            price1 = int(price1[:space - 1])
             prices1.append(price1)
 
-
     # Begin Element-wise substraction of new condition items price list from new&used items price list:
     print(len(prices), 'NEW & USED')
     print(len(prices1), 'NEW')
@@ -122,7 +124,8 @@ while True:
         prices.remove(element)
 
     if 'NEW' in SQ:
-        kde_datapoints = sns.kdeplot(prices1, shade = True).get_lines()[0].get_data()
+        kde_datapoints = sns.kdeplot(prices1, shade=True).get_lines()[
+            0].get_data()
         sns.rugplot(prices1)
         print(str(len(prices1)) + " Results" + "\n")
         print("Average Price Sold New = $" + str(np.mean(prices1)) + "\n")
@@ -134,7 +137,8 @@ while True:
         kde_y = kde_datapoints[1]
         optimal_price = kde_x[np.argmax(kde_y)]
         print("Optimal Price New = $" + str(optimal_price) + "\n")
-        print("Optimal Price Including Shipping New = $" + str(optimal_price + 6.79) + "\n")
+        print("Optimal Price Including Shipping New = $" +
+              str(optimal_price + 6.79) + "\n")
         print("URL Link (New): " + url_1b + "\n")
         plt.ylabel('KDE')
         plt.xlabel('Price ($)')
@@ -142,7 +146,8 @@ while True:
     else:
         try:
 
-            kde_datapoints = sns.kdeplot(prices, shade = True).get_lines()[0].get_data()
+            kde_datapoints = sns.kdeplot(prices, shade=True).get_lines()[
+                0].get_data()
             sns.rugplot(prices)
             print(str(len(prices)) + " Results" + "\n")
             print("Average Price Sold Used = $" + str(np.mean(prices)) + "\n")
@@ -156,7 +161,8 @@ while True:
             kde_y = kde_datapoints[1]
             optimal_price = kde_x[np.argmax(kde_y)]
             print("Optimal Price Used = $" + str(optimal_price) + "\n")
-            print("Optimal Price Including Shipping Used = $" + str(optimal_price + 6.79) + "\n")
+            print("Optimal Price Including Shipping Used = $" +
+                  str(optimal_price + 6.79) + "\n")
             print("URL Link: " + url_a + "\n")
             plt.ylabel('KDE')
             plt.xlabel('Price ($)')

posh.py

@@ -6,10 +6,10 @@ import concurrent.futures
 import numpy as np
 # import matplotlib.pyplot as plt
 
+search_query = str(input('Title Search: '))
 
-def main():
     
-    def url_base_builder(search_query):
+def url_base_builder(search_query):
     genders = ['Men', 'Women']
 
     posh_colors = ['Red', 'Pink', 'Orange', 'Yellow', 'Green', 'Blue', 'Purple',
@@ -43,7 +43,7 @@ def main():
     return all_sold_url_base, new_sold_url_base
 
 
-    def all_sold_list_builder(i):
+def all_sold_list_builder(i):
     bases = url_base_builder(search_query)
     all_sold_url_base = bases[0]
     all_sold_prices = []
@@ -53,15 +53,18 @@ def main():
     # last_page = soup.find(string = re.compile('No Listings Found'))
     for price in soup.find_all('span', {'class': 'p--t--1 fw--bold'}):
         price = price.get_text()
-            dollar_index = price.find('$')
+        price = re.findall(r'[^\$]\d+', price)[0]
-            price = price[dollar_index+1:]
+        price = float(price)
-            space = price.find(' ')
+        # dollar_index = price.find('$')
-            price = int(price[:space-1])
+        # price = price[dollar_index+1:]
+        # space = price.find(' ')
+        # price = int(price[:space-1])
         all_sold_prices.append(price)
+    # all_sold_prices = list(map(float, re.findall(r'[^\$]\d+[.]\d+', html)))
     return all_sold_prices
 
 
-    def new_sold_list_builder(i):
+def new_sold_list_builder(i):
     bases = url_base_builder(search_query)
     new_sold_url_base = bases[1]
     new_sold_prices = []
@@ -69,24 +72,24 @@ def main():
     html = requests.get(url).text
     soup = b(html, "lxml")
     # last_page = soup.find(string = re.compile('No Listings Found'))#this is present in all pages that don't have a full 48 listings on them. So you end up with an empty price list becuase of your conditional statement
+    # new_sold_prices = list(map(float, re.findall(r'[^\$]\d+[.]\d+', html)))
 
     for price in soup.find_all('span', {'class': 'p--t--1 fw--bold'}):
         price = price.get_text()
-            dollar_index = price.find('$')
+        price = re.findall(r'[^\$]\d+', price)[0]
-            price = price[dollar_index+1:]
+        price = float(price)
-            space = price.find(' ')
+        # dollar_index = price.find('$')
-            price = int(price[:space-1])
+        # price = price[dollar_index+1:]
+        # space = price.find(' ')
+        # price = int(price[:space-1])
         new_sold_prices.append(price)
     return new_sold_prices
 
-    search_query = str(input('Title Search: '))
+
+def main():
   
     start = time.time()
 
-    page_list = list(range(1, 5))
-    all_sold_list = []
-    new_sold_list = []
-
     with concurrent.futures.ThreadPoolExecutor() as executor:
         for future in executor.map(all_sold_list_builder, page_list):
             all_sold_list.extend(future)
@@ -115,7 +118,12 @@ def main():
     print('Average New Sold Price', average_new_sold_price, new_sold_results)
     print(total_results)
 
+
 if __name__ == '__main__':
+    
+    page_list = list(range(1, 5))
+    all_sold_list = []
+    new_sold_list = []
     main()
 
 

posh.py~

@@ -0,0 +1,130 @@
+import requests
+from bs4 import BeautifulSoup as b
+import time
+import re
+import concurrent.futures
+import numpy as np
+# import matplotlib.pyplot as plt
+
+search_query = str(input('Title Search: '))
+
+    
+def url_base_builder(search_query):
+    genders = ['Men', 'Women']
+
+    posh_colors = ['Red', 'Pink', 'Orange', 'Yellow', 'Green', 'Blue', 'Purple',
+                'Gold', 'Silver', 'Black', 'Gray', 'White', 'Cream', 'Brown', 'Tan']
+
+    for i in range(0, len(posh_colors)):
+        if posh_colors[i] in search_query:
+            url_color = '&color[]=' + posh_colors[i]
+            color = posh_colors[i]
+            break
+        else:
+            color = ''
+            url_color = ''
+    for i in range(0, len(genders)):
+        if genders[i] in search_query:
+            url_gender = '&department=' + genders[i]
+            gender = genders[i]
+            break
+        else:
+            gender = ''
+            url_gender = '&department=All'
+
+    sq = search_query.replace(color, '').replace(gender, '').replace('NEW', '').replace(' ', '+')
+
+    all_sold_url_base = 'https://poshmark.com/search?query=' + sq + \
+        "&availability=sold_out" + url_color + url_gender + '&max_id='
+
+    new_sold_url_base = 'https://poshmark.com/search?query=' + sq + '&availability=sold_out' + \
+        '&condition=nwt_and_ret' + url_color + url_gender + '&max_id='
+
+    return all_sold_url_base, new_sold_url_base
+
+
+def all_sold_list_builder(i):
+    bases = url_base_builder(search_query)
+    all_sold_url_base = bases[0]
+    all_sold_prices = []
+    url = all_sold_url_base + str(i)
+    html = requests.get(url).text
+    soup = b(html, "lxml")
+    # last_page = soup.find(string = re.compile('No Listings Found'))
+    for price in soup.find_all('span', {'class': 'p--t--1 fw--bold'}):
+        price = price.get_text()
+        price = re.findall(r'[^\$]\d+', price)[0]
+        price = float(price)
+        # dollar_index = price.find('$')
+        # price = price[dollar_index+1:]
+        # space = price.find(' ')
+        # price = int(price[:space-1])
+        all_sold_prices.append(price)
+    # all_sold_prices = list(map(float, re.findall(r'[^\$]\d+[.]\d+', html)))
+    return all_sold_prices
+
+
+def new_sold_list_builder(i):
+    bases = url_base_builder(search_query)
+    new_sold_url_base = bases[1]
+    new_sold_prices = []
+    url = new_sold_url_base + str(i)
+    html = requests.get(url).text
+    soup = b(html, "lxml")
+    # last_page = soup.find(string = re.compile('No Listings Found'))#this is present in all pages that don't have a full 48 listings on them. So you end up with an empty price list becuase of your conditional statement
+    # new_sold_prices = list(map(float, re.findall(r'[^\$]\d+[.]\d+', html)))
+
+    for price in soup.find_all('span', {'class': 'p--t--1 fw--bold'}):
+        price = price.get_text()
+        price = re.findall(r'[^\$]\d+', price)[0]
+        price = float(price)
+        # dollar_index = price.find('$')
+        # price = price[dollar_index+1:]
+        # space = price.find(' ')
+        # price = int(price[:space-1])
+        new_sold_prices.append(price)
+    return new_sold_prices
+
+
+def main():
+  
+    start = time.time()
+
+    with concurrent.futures.ThreadPoolExecutor() as executor:
+        for future in executor.map(all_sold_list_builder, page_list):
+            all_sold_list.extend(future)
+
+    with concurrent.futures.ThreadPoolExecutor() as executor:
+        for future in executor.map(new_sold_list_builder, page_list):
+            new_sold_list.extend(future)# if you can pull the nwt price simultaneously with used then you won't have to use this
+
+
+    for element in new_sold_list:
+        all_sold_list.remove(element)
+    used_sold_list = all_sold_list
+
+    average_used_sold_price = '$' + str(round(np.mean(used_sold_list), 2))
+    average_new_sold_price = '$' + str(round(np.mean(new_sold_list), 2))
+
+    used_sold_results = str(len(used_sold_list)) + ' Used Results'
+    new_sold_results = str(len(new_sold_list)) + ' NWT Results'
+    total_results = str(len(used_sold_list) + len(new_sold_list)) + ' Total Results'
+
+    end = time.time()
+
+    print(end - start, 'seconds')
+
+    print('Average Used Sold Price', average_used_sold_price, used_sold_results)
+    print('Average New Sold Price', average_new_sold_price, new_sold_results)
+    print(total_results)
+
+
+if __name__ == '__main__':
+    
+    page_list = list(range(1, 5))
+    all_sold_list = []
+    new_sold_list = []
+    main()
+
+
+'''to speed up the program you can include a few things: 1) only parse the total results and sift for the NWT listings to create a separate NWT list 2) Implement processpoolexecutor to use more than one worker to parse the pages 3) find a better way to find the last page so you don't have to make more requests than necessary. This could be either taking the "smallest" "no listings found" page of the pages while excluding the others after the smallest one is found. Or, determining from the request headers whether a page is worth downloading or not 4) using a while loop in chunks of 2-4 pages to find the last page in conjunction with number 3'''

poshare.py

@@ -11,29 +11,53 @@ from selenium.webdriver.common.keys import Keys
 from bs4 import BeautifulSoup as b
 import time
 from selenium.common.exceptions import ElementClickInterceptedException
+import winsound
 
-browser = webdriver.Firefox(executable_path="C:/Users/unknown/Desktop/projects/geckodriver")
+
+browser = webdriver.Firefox(executable_path="C:/Users/unknown/Desktop/projects/poshmark/geckodriver")
 wait = WebDriverWait(browser, 30)
 browser.get('https://poshmark.com/login')
 usename = browser.find_element_by_id('login_form_username_email')
 usename.send_keys('SpeanutButter')
 psw = browser.find_element_by_id('login_form_password')
 psw.send_keys('***REMOVED***')
+iframe = 'default value'
+
+def reCaptcha_finder(): # Still not working. Works on the first recaptcha popup but not second one for some reason
+    global iframe
+    time.sleep(4)
+    iframes = browser.find_elements_by_tag_name('iframe')
+    for frame in iframes:
+        if not iframe in iframes:
+            browser.switch_to.frame(frame)
+            try:
+                browser.find_element_by_xpath('//label[text()="I\'m not a robot"]')
+                winsound.Beep(540, 1000)
+                iframe = frame
+                input('Complete reCaptcha then press "enter" to continue')
+                browser.switch_to.default_content()
+                break
+            except NoSuchElementException:
+                browser.switch_to.default_content()
+
 psw.submit()
-input('press "enter" to continue')
+
+reCaptcha_finder()
+# have to find different element for log in after recaptcha is completed. Do manually for now
+
 wait.until(EC.presence_of_element_located((By.XPATH, "//title[text()='Feed - Poshmark']")))
 browser.get('https://poshmark.com/closet/speanutbutter?department=Women&sort_by=price_desc')
 input('press "enter" to continue')
 
 html = browser.page_source
-soup = b(html)
+soup = b(html, "lxml")
 elm = browser.find_element_by_tag_name('html')
-while not soup.find('i', text = "Not for Sale"):
+while not soup.find('span', text="Not for Sale"):
     elm.send_keys(Keys.END)
     html = browser.page_source
     soup = b(html)
-list_titles = soup.find_all('a',{'class':'title'})
+list_titles = soup.find_all('a', {'class': 'title'})
-active_listings = soup.find_all('i', {'class':"icon share-gray"})
+active_listings = soup.find_all('i', {'class': "icon share-gray"})
 print(len(active_listings))
 container = browser.find_elements_by_xpath("//div[@id='tiles-con']/div")
 i = -1
@@ -50,39 +74,29 @@ for divs in container:
                 pass
         except NoSuchElementException:
             share = divs.find_element_by_xpath(".//i[@class = 'icon share-gray']")
-                time.sleep(random.uniform(.6,1.2))
+            time.sleep(random.uniform(.6, 1.2))
             try:
                 share.click()
-                    if soup.find('input', id = "recaptcha-token"):
+                # reCaptcha_finder() # Might only need reCaptcha_finder() here and not afterwards or the other way around. Pay attention to where the recaptcha occurs
-                        input('Finish recapcha and press "enter" to continue')
-                    if soup.find('span', text = "I'm not a robot"):
-                        input('Finish recapcha and press "enter" to continue')
                 if share_to == 'F':
                     wait.until(EC.presence_of_element_located((By.XPATH, "//span[text()='To My Followers']")))
                     share = browser.find_element_by_xpath("//span[text()='To My Followers']")
-                        time.sleep(random.uniform(.6,1.2))
+                    time.sleep(random.uniform(.6, 1.2))
                     share.click()
-
+                    reCaptcha_finder()
-                        if soup.find('input', id = "recaptcha-token"):
-                            input('Finish recapcha and press "enter" to continue')
                     print(i)
-                        if soup.find('span', text = "I'm not a robot"):
-                            input('Finish recapcha and press "enter" to continue')
                     title = list_titles[i].get_text()
                     print(title)
                 if share_to == 'P':
                     wait.until(EC.presence_of_element_located((By.XPATH, "//*[contains(text(), 'Happening Now')]")))
                     share = browser.find_element_by_xpath("//*[contains(text(), 'Happening Now')]")
-                        time.sleep(random.uniform(.6,1.2))
+                    time.sleep(random.uniform(.6, 1.2))
                     share.click()
-                        if soup.find('input', id = "recaptcha-token"):
+                    reCaptcha_finder()
-                            input('Finish recapcha and press "enter" to continue')
-                        if soup.find('span', text = "I'm not a robot"):
-                            input('Finish recapcha and press "enter" to continue')
                     print(i)
                     title = list_titles[i].get_text()
                     print(title)
             except ElementClickInterceptedException:
                 pass
 
-'''If poshmark lets you browser.get any page then you should skip the pagination loading to load all the pages and then just go through each page and share that way. It wouldn't be such a time consuming process'''
+# If poshmark lets you browser.get any page then you should skip the pagination loading to load all the pages and then just go through each page and share that way. It wouldn't be such a time consuming process

poshlogin_requests.py

@@ -0,0 +1,2 @@
+import requests
+import 

sharevision.ipynb

@@ -0,0 +1,141 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from selenium import webdriver\n",
+    "from selenium.webdriver.common.keys import Keys\n",
+    "from selenium.webdriver.support.select import Select\n",
+    "from selenium.webdriver.common.by import By\n",
+    "from selenium.webdriver.support.ui import WebDriverWait\n",
+    "from selenium.webdriver.support import expected_conditions as EC\n",
+    "from selenium.webdriver.common.action_chains import ActionChains\n",
+    "import random\n",
+    "from selenium.common.exceptions import NoSuchElementException\n",
+    "from selenium.webdriver.common.keys import Keys\n",
+    "from bs4 import BeautifulSoup as b\n",
+    "import time\n",
+    "from selenium.common.exceptions import ElementClickInterceptedException\n",
+    "import winsound"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "browser = webdriver.Firefox(executable_path=\"C:/Users/unknown/Desktop/projects/poshmark/geckodriver\")\n",
+    "wait = WebDriverWait(browser, 30)\n",
+    "browser.get('https://poshmark.com/login')\n",
+    "usename = browser.find_element_by_id('login_form_username_email')\n",
+    "usename.send_keys('SpeanutButter')\n",
+    "psw = browser.find_element_by_id('login_form_password')\n",
+    "psw.send_keys('***REMOVED***')\n",
+    "iframe = 'default value'\n",
+    "page_number = list(range(1,18))\n",
+    "base_url = 'https://poshmark.com/closet/speanutbutter?availability=available&sort_by=price_desc&all_size=true&max_id='\n",
+    "\n",
+    "def reCaptcha_finder(): # Still not working. Works on the first recaptcha popup but not second one for some reason\n",
+    "    global iframe\n",
+    "    time.sleep(4)\n",
+    "    iframes = browser.find_elements_by_tag_name('iframe')\n",
+    "    for frame in iframes:\n",
+    "        if not iframe in iframes:\n",
+    "            browser.switch_to.frame(frame)\n",
+    "            try:\n",
+    "                browser.find_element_by_xpath('//label[text()=\"I\\'m not a robot\"]')\n",
+    "                winsound.Beep(540, 1000)\n",
+    "                iframe = frame\n",
+    "                input('Complete reCaptcha then press \"enter\" to continue')\n",
+    "                browser.switch_to.default_content()\n",
+    "                break\n",
+    "            except NoSuchElementException:\n",
+    "                browser.switch_to.default_content()\n",
+    "\n",
+    "psw.submit()\n",
+    "\n",
+    "reCaptcha_finder()\n",
+    "\n",
+    "wait.until(EC.presence_of_element_located((By.XPATH, \"//title[text()='Feed - Poshmark']\")))\n",
+    "\n",
+    "\n",
+    "for page in page_number:\n",
+    "    \n",
+    "    browser.get(base_url+str(page))\n",
+    "    input('press \"enter\" to continue')\n",
+    "\n",
+    "    html = browser.page_source\n",
+    "    soup = b(html, \"lxml\")\n",
+    "\n",
+    "    list_titles = soup.find_all('a', {'class': 'title'})\n",
+    "    active_listings = soup.find_all('i', {'class': \"icon share-gray\"})\n",
+    "    print(len(active_listings))\n",
+    "    container = browser.find_elements_by_xpath(\"//div[@id='tiles-con']/div\")\n",
+    "    i = -1\n",
+    "    share_to = input('share to followers (F) or share to party (P)?: ')\n",
+    "\n",
+    "    for divs in container:\n",
+    "        i += 1\n",
+    "        wait.until(EC.presence_of_element_located((By.XPATH, \".//i[@class = 'icon share-gray']\")))\n",
+    "        try:\n",
+    "            if divs.find_element_by_xpath(\".//i[@class = 'icon inventory-tag not-for-sale-tag']\"):\n",
+    "                pass\n",
+    "        except NoSuchElementException:\n",
+    "            try:\n",
+    "                if divs.find_element_by_xpath(\".//i[@class = 'icon inventory-tag sold-tag']\"):\n",
+    "                    pass\n",
+    "            except NoSuchElementException:\n",
+    "                share = divs.find_element_by_xpath(\".//i[@class = 'icon share-gray']\")\n",
+    "                time.sleep(random.uniform(.6, 1.2))\n",
+    "                try:\n",
+    "                    share.click()\n",
+    "                    # reCaptcha_finder() # Might only need reCaptcha_finder() here and not afterwards or the other way around. Pay attention to where the recaptcha occurs\n",
+    "                    if share_to == 'F':\n",
+    "                        wait.until(EC.presence_of_element_located((By.XPATH, \"//span[text()='To My Followers']\")))\n",
+    "                        share = browser.find_element_by_xpath(\"//span[text()='To My Followers']\")\n",
+    "                        time.sleep(random.uniform(.6, 1.2))\n",
+    "                        share.click()\n",
+    "                        reCaptcha_finder()\n",
+    "                        print(i)\n",
+    "                        title = list_titles[i].get_text()\n",
+    "                        print(title)\n",
+    "                    if share_to == 'P':\n",
+    "                        wait.until(EC.presence_of_element_located((By.XPATH, \"//*[contains(text(), 'Happening Now')]\")))\n",
+    "                        share = browser.find_element_by_xpath(\"//*[contains(text(), 'Happening Now')]\")\n",
+    "                        time.sleep(random.uniform(.6, 1.2))\n",
+    "                        share.click()\n",
+    "                        reCaptcha_finder()\n",
+    "                        print(i)\n",
+    "                        title = list_titles[i].get_text()\n",
+    "                        print(title)\n",
+    "                except ElementClickInterceptedException:\n",
+    "                    pass\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "scrapers",
+   "language": "python",
+   "name": "scrapers"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}